Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ZaxbyHub/opencode-swarm --skill orchestrating-subagentsgit clone --depth 1 https://github.com/ZaxbyHub/opencode-swarmWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zaxbyhub/opencode-swarm/orchestrating-subagents)<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/orchestrating-subagents"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/orchestrating-subagents.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.01373 |
| Opus 5 | $0.00050 | $0.00687 |
| Sonnet 5 | $0.00020 | $0.00275 |
| Haiku 4.5 | $0.00010 | $0.00137 |
Grade A, and why
orchestrating-subagents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrating Subagents
Swarm-mode work in this repo delegates heavily (explorer → reviewer → critic).
This skill defines HOW to delegate so validation gates stay strong while
breadth stays fast and cheap. It complements — never replaces — the gates in
.claude/session/swarm-mode.md, qa-sweep, and swarm-implement.
Role → tier mapping
| Role | Agent type | Model / effort | Rationale |
|---|---|---|---|
| Explorer (mapping, candidate findings) | Explore when read-only suffices |
Cheaper/faster tier acceptable; low–medium effort | Recall-bound, not reasoning-bound; the reviewer gate catches misses |
| Implementer (scoped edits) | general-purpose | Session model; medium–high effort | Edits need project conventions (CLAUDE.md context) |
| Reviewer (independent validation) | general-purpose, fresh context | Session (strongest) model; high effort | Precision-bound; false approvals are the expensive failure |
| Critic (final challenge) | general-purpose, fresh context | Session (strongest) model; high effort | Same — this is the last line of defense |
Hard rule: economize on explorers, never on reviewers or critics. If the
harness exposes model or effort overrides for subagents, tier explorers down;
do not tier the reviewer or critic below the session model or below high
effort. If no override is available, tier by agent type (Explore is
lightweight: read-only tools, skips CLAUDE.md) and by prompt scope.
Fan-out discipline
- Launch parallel agents only for disjoint scopes. Before launching, write one line per agent stating its scope; if two overlap, merge them.
- 2–4 explorers per wave is a heuristic only when the active workflow does not define its own fan-out contract. A workflow-specific contract overrides this heuristic: PR review, for example, requires all six base dimensions and all eleven risk families to be covered on every PR — its capability profiles and depth tiers (see swarm-pr-review) govern how many lanes carry that coverage, and under the plugin's mechanical controller the tier is computed from the bound diff and the matching lane floors are enforced outright. No time, cost, repository-size, or simplicity rationale may reduce the coverage a workflow mandates. Outside fixed-fan-out workflows, more agents than distinct scopes adds token cost and synthesis burden without adding recall.
- Launch independent agents in a single message so they run concurrently.
- Do not re-run a search an agent is already doing; wait for its report.
- Scale waves, not width: if the first wave surfaces new territory, launch a second targeted wave rather than one giant speculative first wave.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 114 lines · 100 tokens per session scan A f8586722c6c2
orchestrating-subagents is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (463 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,373 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
armada-contract
Co-write an armada contract (REQUIREMENTS.md) one question at a time. Use when drafting or updating a feature contract before implementation.
armada-gate
Run an evidence-gate checklist for each success criterion in the current phase. Use when checking if a phase is complete before marking it passed.
selftune
Self-improving skills toolkit that watches real agent sessions, detects missed triggers, grades execution quality, and improves skill packages through evals, replay, baselines, review, and post-deploy watch. Use when verifying or publishing a skill, improving instructions or routing, checking skill health, grading…
armada-dispatch
Dispatch subagents in parallel with disjoint file scope. Use when facing 2+ independent tasks, multiple files, or parallel phases. Triggers on: parallelize, dispatch subagents, run in parallel.
armada-ledger
Pick the right ledger for a finding. Use when writing defects, adversarial findings, or security findings. Triggers on: ledger, defect, adversarial, security finding, DEF-001, ADV-001, SEC-001.
armada-ponytail
Minimal, pragmatic code discipline for Clipper and Galleon. Laziest working solution, no fluff, no YAGNI bloat.